mirror of
https://github.com/ollama/ollama.git
synced 2026-07-23 09:10:53 -05:00
Add experimental image generation fields to /api/generate (#13753)
Request fields (experimental): - width: image width (max 4096) - height: image height (max 4096) - steps: denoising steps - seed: random seed Response fields (experimental): - images: base64-encoded generated images - completed: current step progress - total: total steps Other changes: - Fix lifecycle bug where image models wouldn't unload (refCount issue) - Fix "headers already written" error on Ctrl+C during streaming - Add gin middleware for OpenAI /v1/images/generations compatibility - Update CLI to use /api/generate with progress bar - Add preload support in interactive mode
This commit is contained in:
@@ -737,3 +737,60 @@ func FromCompleteRequest(r CompletionRequest) (api.GenerateRequest, error) {
|
||||
DebugRenderOnly: r.DebugRenderOnly,
|
||||
}, nil
|
||||
}
|
||||
|
||||
// ImageGenerationRequest is an OpenAI-compatible image generation request.
|
||||
type ImageGenerationRequest struct {
|
||||
Model string `json:"model"`
|
||||
Prompt string `json:"prompt"`
|
||||
N int `json:"n,omitempty"`
|
||||
Size string `json:"size,omitempty"`
|
||||
ResponseFormat string `json:"response_format,omitempty"`
|
||||
Seed *int64 `json:"seed,omitempty"`
|
||||
}
|
||||
|
||||
// ImageGenerationResponse is an OpenAI-compatible image generation response.
|
||||
type ImageGenerationResponse struct {
|
||||
Created int64 `json:"created"`
|
||||
Data []ImageURLOrData `json:"data"`
|
||||
}
|
||||
|
||||
// ImageURLOrData contains either a URL or base64-encoded image data.
|
||||
type ImageURLOrData struct {
|
||||
URL string `json:"url,omitempty"`
|
||||
B64JSON string `json:"b64_json,omitempty"`
|
||||
}
|
||||
|
||||
// FromImageGenerationRequest converts an OpenAI image generation request to an Ollama GenerateRequest.
|
||||
func FromImageGenerationRequest(r ImageGenerationRequest) api.GenerateRequest {
|
||||
req := api.GenerateRequest{
|
||||
Model: r.Model,
|
||||
Prompt: r.Prompt,
|
||||
}
|
||||
// Parse size if provided (e.g., "1024x768")
|
||||
if r.Size != "" {
|
||||
var w, h int32
|
||||
if _, err := fmt.Sscanf(r.Size, "%dx%d", &w, &h); err == nil {
|
||||
req.Width = w
|
||||
req.Height = h
|
||||
}
|
||||
}
|
||||
if r.Seed != nil {
|
||||
if req.Options == nil {
|
||||
req.Options = map[string]any{}
|
||||
}
|
||||
req.Options["seed"] = *r.Seed
|
||||
}
|
||||
return req
|
||||
}
|
||||
|
||||
// ToImageGenerationResponse converts an Ollama GenerateResponse to an OpenAI ImageGenerationResponse.
|
||||
func ToImageGenerationResponse(resp api.GenerateResponse) ImageGenerationResponse {
|
||||
var data []ImageURLOrData
|
||||
if resp.Image != "" {
|
||||
data = []ImageURLOrData{{B64JSON: resp.Image}}
|
||||
}
|
||||
return ImageGenerationResponse{
|
||||
Created: resp.CreatedAt.Unix(),
|
||||
Data: data,
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user